Search

The recent years there is rise of all-flash data storage. Flash disk has significant advantages comparing to HDD. This motivates to migrate existing and develop new high load systems basing on all-flash storage. Thus, one should choose an appropriate storage architecture to balance cost, throughput, load, performance, etc. In this paper we present mathematical models which describe reliability, performance and cost of all-flash data storage. Also, we provide results of simulations, analysis and recommendations for various usage scenarios. The results of this study support development of smart sensors for Internet of Things, where all-flash data storage is used to maintain sensed data locally.

Nowadays there are a lot of car sharing service provider have been appeared in Russian market as well as in the world. Car sharing become popular since a person can have comfortable and quick transportation means in the city. This transportation means allow him/her to reach destinations without owning a private vehicle. However, sometimes for the car sharing user it is not possible to find a car in nearest location. In this case the car sharing company can propose customers who goes to the same destination to share the ride together with the travel expenses. The paper proposes an approach to matching of driver and pedestrian routes based on predefined constraints such as detours and additional time the customers are going to spend for ride sharing.

We investigate the influence of latency and wearout of writing data on the efficiency of high-performance data storage systems. Using a mathematical model, we propose the strategy of redundant writing with cancelling long write operations. Pre- sented numerical simulation results allow choosing the replication level needed to achieve the trade-off between the latency and wearout that provides desired reliability and efficiency.

The logical and physical topology description of an enterprise computer network is required for many network management tasks. However, the automatized building of such description is complicated due to the connectivity data incompleteness. This leads to the necessity of solving the problem of incomplete data improvement. In this paper we used previous works on the network modeling and commonly used reachability set abstraction to solve the denoted problem. The contribution of this paper is a criterion for determining when the connectivity data is sufficient for building topology descriptions and the algorithm for incomplete data improvement based on the criteria. The algorithm implementation test and evaluations provided in the paper show its correctness, applicability for using in the real enterprise networks and its greater effectiveness comparing to the other existing methods.

In mobile traffic transmission networks, the limited allotted spectrum-involving voice communication and data communication-is faced with the problem of limited bandwidth and consequent traffic congestion. The problem leads to poor communication services like incomplete calls, call drops, slower Internet speed, higher cost of internet service, and other undesirable effects by the service providers. The bandwidth saturation and congestion conundrum still remains critical research area, especially with emerging multitude of edge and intermediate Internet devices. Due to introduction of fog computing such devices become active participants of mobile traffic transmission. In this paper, we consider the Data Interleaving Technique in Mobile Communication (DITMC) and introduce the DITMC-based methodology for reducing the data traffic congestion and bandwidth saturation in GSM networks. The methodology is supported with an Erlang formula model, and our simulation experiments indicate the efficiency. We show that the use of methodology can be extended to other Internet problems like multi-path routing of data streams, active subscription control in smart spaces, and possibility to delegate supplementary processing to edge devices.

Data deduplication importance is growing with the growth of data volumes. The domain of data deduplication is in active development. Recently it was influenced by appearance of Solid State Drive. This new type of disk has significant differences from random access memory and hard disk drives and is widely used now. In this paper we propose a novel taxonomy which reflects the main issues related to deduplication in Solid State Drive. We present a survey on deduplication techniques focusing on flash-based storage. We also describe several Open Source tools implementing data deduplication and briefly describe open research problems related to data deduplication in flash-based storage systems.

This paper presents an approach for robots selforganization for pick-and-place scenario based on Smart-M3 information sharing platform that provide possibilities of information sharing between different services in smart space. In scope of the approach the reference model for robots selforganization has been developed. To provide semantic interoperability, the ontologies for the robots participating in the scenario, have been built. The scenario implementation is based on Lego® Mindstorms EV3 set for robot construction, which is one of the most popular sets for education at the moment.

The paper presents category classification of mobile travel applications accessible at the moment for tourists in application stores for most popular mobile operation systems (Android and iOS). The most interesting category is "Travel Guides" that combines "Information Resources" and "Location-Based Services" category. Authors propose application "Tourist assistant - TAIS" that is related to "Travel Guides" category and recommends the tourist attractions around. Information about attractions is extracted from different internet sources.

The paper summarizes success stories of Finnish and Russian research organizations that joined forces towards development of leading-edge ICT competences and their use in multidisciplinary applications. The partner organizations from both countries have developed close collaboration framework, which enabled them to implement three crossborder cooperation projects co-funded by the Karelia ENPI CBC Programme. The paper describes this framework as a complex combination of various activities, including educational events, practical R&D, as well as infrastructure development and dissemination activities. Following the development of regional cooperation ecosystem and enhancement of ICT competences (KA179 project), rest of the activities were focused on practical and multidisciplinary applications. In these projects, novel approaches and latest information and Internet technologies were used to increase regional tourism attractiveness (KA322 project) and to improve quality of life for people with disabilities by addressing issues related to social exclusion, accessibility and mobility (KA432 project). The aim of the paper is to share practical experiences, gained during implementation of these cross-border cooperation projects, and to present developed ICT applications in a multidisciplinary context.

The paper describes research and development of software platform for optimal operation planning of pulp-and-paper and forestry enterprises using cloud computing technology. This work is a part of long-term activity carried out by Petrozavodsk State University (PetrSU) in the field of scientific research, software development and customer projects for enterprises of pulp-and-paper and forestry industry of Russia. The Platform uses advanced mathematical models and optimization algorithms developed by IT-park of PetrSU to create services for solving a series of planning tasks for different industries: production of corrugated packaging, sawmill, plywood production, timber enterprise.

The paper describes research and development of software system for optimal planning of sawmill operation. This work is a part of long-term activity carried out by Petrozavodsk State University (PetrSU) in the field of scientific research, software development and customer projects for enterprises of pulp-and-paper and forestry industry of Russia. The system uses advanced mathematical models and optimization algorithms, developed by IT-park of PetrSU, to solve a series of planning tasks for any number of orders and any configuration of process equipment of a hardwood sawmill. The developed mathematical model takes into account all features, limitations and parameters of process equipment, as well as of raw material and production orders. The efficiency of solutions had been validated on real production data of several sawmills in Russia. The system has friendly and flexible user interface and can be easily modified to handle new customer-specific requirements.